{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XDL2B5WJJ2EDQZ2E4OLSDGQDQ5","short_pith_number":"pith:XDL2B5WJ","schema_version":"1.0","canonical_sha256":"b8d7a0f6c94e88386744e397219a03874bc4456f66e100ed9c968dadf384ec3a","source":{"kind":"arxiv","id":"2206.07898","version":1},"attestation_state":"computed","paper":{"title":"Multimodal Dialogue State Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Hung Le, Nancy F. Chen, Steven C.H. Hoi","submitted_at":"2022-06-16T03:18:42Z","abstract_excerpt":"Designed for tracking user goals in dialogues, a dialogue state tracker is an essential component in a dialogue system. However, the research of dialogue state tracking has largely been limited to unimodality, in which slots and slot values are limited by knowledge domains (e.g. restaurant domain with slots of restaurant name and price range) and are defined by specific database schema. In this paper, we propose to extend the definition of dialogue state tracking to multimodality. Specifically, we introduce a novel dialogue state tracking task to track the information of visual objects that ar"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.07898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-06-16T03:18:42Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"04c80f523b8d0d22dbdefdb70f4ccd1ed22aa13b5dff88e1c092e615255417e6","abstract_canon_sha256":"631548a9f6ccfcef95d35b4764b819ed6668f7fe4048ce131097ba30d20582a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:19.667088Z","signature_b64":"rM18/aluSPFsOtLpWvCT1ORQ3gKTWIp9ZFdP6tD9ilCz7IetggxO3JQok4lKzhqlu0QGe8Xo6Bc0wEtaZnldDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8d7a0f6c94e88386744e397219a03874bc4456f66e100ed9c968dadf384ec3a","last_reissued_at":"2026-07-05T04:32:19.666594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:19.666594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Dialogue State Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Hung Le, Nancy F. Chen, Steven C.H. Hoi","submitted_at":"2022-06-16T03:18:42Z","abstract_excerpt":"Designed for tracking user goals in dialogues, a dialogue state tracker is an essential component in a dialogue system. However, the research of dialogue state tracking has largely been limited to unimodality, in which slots and slot values are limited by knowledge domains (e.g. restaurant domain with slots of restaurant name and price range) and are defined by specific database schema. In this paper, we propose to extend the definition of dialogue state tracking to multimodality. Specifically, we introduce a novel dialogue state tracking task to track the information of visual objects that ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07898","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.07898/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.07898","created_at":"2026-07-05T04:32:19.666655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07898v1","created_at":"2026-07-05T04:32:19.666655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07898","created_at":"2026-07-05T04:32:19.666655+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDL2B5WJJ2ED","created_at":"2026-07-05T04:32:19.666655+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDL2B5WJJ2EDQZ2E","created_at":"2026-07-05T04:32:19.666655+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDL2B5WJ","created_at":"2026-07-05T04:32:19.666655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05806","citing_title":"Divide-and-Conquer: Tree-structured Strategy with Answer Distribution Estimator for Goal-Oriented Visual Dialogue","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5","json":"https://pith.science/pith/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5.json","graph_json":"https://pith.science/api/pith-number/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5/graph.json","events_json":"https://pith.science/api/pith-number/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5/events.json","paper":"https://pith.science/paper/XDL2B5WJ"},"agent_actions":{"view_html":"https://pith.science/pith/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5","download_json":"https://pith.science/pith/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5.json","view_paper":"https://pith.science/paper/XDL2B5WJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07898&json=true","fetch_graph":"https://pith.science/api/pith-number/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5/action/storage_attestation","attest_author":"https://pith.science/pith/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5/action/author_attestation","sign_citation":"https://pith.science/pith/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5/action/citation_signature","submit_replication":"https://pith.science/pith/XDL2B5WJJ2EDQZ2E4OLSDGQDQ5/action/replication_record"}},"created_at":"2026-07-05T04:32:19.666655+00:00","updated_at":"2026-07-05T04:32:19.666655+00:00"}